© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fazenda
    -1.21
    ร้าน
    -1.16
    ()]
    -1.16
    días
    -1.15
    tagHelper
    -1.13
    覧
    -1.13
     خریدار
    -1.12
    varande
    -1.12
    近年来
    -1.09
    Έ
    -1.09
    POSITIVE LOGITS
    /
    1.35
    Which
    1.32
    which
    1.26
    Should
    1.24
     нормы
    1.23
    Could
    1.21
    Would
    1.20
    how
    1.20
    すっ
    1.20
    割と
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.